+ Reply to Thread
Page 1 of 2 1 2 LastLast
Results 1 to 15 of 16

Thread: hierarchical regression for controlling variables?

  1. #1
    Points: 95, Level: 1
    Level completed: 90%, Points required for next Level: 5

    Posts
    13
    Thanks
    0
    Thanked 0 Times in 0 Posts

    hierarchical regression for controlling variables?




    For my dissertation, my supervisor told me to do a regression analysis and control for 2 variables. So should I report in my dissertation that I have done a hierarchical regression analysis or should I report that I have done a standard multiple regression analysis while controlling for the 2 variables?

    I thought reporting that I have done a hierarchical regression analysis is better, what do you think?

  2. #2
    Devorador de queso
    Points: 95,540, Level: 100
    Level completed: 0%, Points required for next Level: 0
    Awards:
    Posting AwardCommunity AwardDiscussion EnderFrequent Poster
    Dason's Avatar
    Location
    Tampa, FL
    Posts
    12,930
    Thanks
    307
    Thanked 2,629 Times in 2,245 Posts

    Re: hierarchical regression for controlling variables?

    If all you did was a multiple regression and included 2 other variables you wanted to control for I don't see how you could call it a hierarchical regression.
    I don't have emotions and sometimes that makes me very sad.

  3. #3
    Points: 95, Level: 1
    Level completed: 90%, Points required for next Level: 5

    Posts
    13
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Re: hierarchical regression for controlling variables?

    I wil explain that more clear:

    she told me to regres the independent variable (x) on the dependent variable (y), and by doing so control for the effects of 2 variables (clicking on "next").
    So my question is whether I should report that I have done a hierarchical multiple regression or a standard multiple regression?

  4. #4
    Omega Contributor
    Points: 38,253, Level: 100
    Level completed: 0%, Points required for next Level: 0
    hlsmith's Avatar
    Location
    Not Ames, IA
    Posts
    6,989
    Thanks
    397
    Thanked 1,185 Times in 1,146 Posts

    Re: hierarchical regression for controlling variables?

    Still sounds like a standard multiple regression (with three DV, two of which were only in the model to control for). I don't think you know what a hierarchical model is, it is something in particular were you are controlling for structural levels. Might help if you list out your DVs.

  5. #5
    Devorador de queso
    Points: 95,540, Level: 100
    Level completed: 0%, Points required for next Level: 0
    Awards:
    Posting AwardCommunity AwardDiscussion EnderFrequent Poster
    Dason's Avatar
    Location
    Tampa, FL
    Posts
    12,930
    Thanks
    307
    Thanked 2,629 Times in 2,245 Posts

    Re: hierarchical regression for controlling variables?

    It's still not clear to me what you've done exactly and why this would be hierarchical at all.
    I don't have emotions and sometimes that makes me very sad.

  6. #6
    Cookie Scientist
    Points: 13,431, Level: 75
    Level completed: 46%, Points required for next Level: 219
    Jake's Avatar
    Location
    Austin, TX
    Posts
    1,293
    Thanks
    66
    Thanked 584 Times in 438 Posts

    Re: hierarchical regression for controlling variables?

    Just describe it in terms of which variables are or are not controlled for. That is the most straightforward and easy to understand description.
    “In God we trust. All others must bring data.”
    ~W. Edwards Deming

  7. #7
    Cookie Scientist
    Points: 13,431, Level: 75
    Level completed: 46%, Points required for next Level: 219
    Jake's Avatar
    Location
    Austin, TX
    Posts
    1,293
    Thanks
    66
    Thanked 584 Times in 438 Posts

    Re: hierarchical regression for controlling variables?

    Dason: I guess it could be thought of as hierarchical in the sense that first covariate 1 was entered, then covariate 2 was entered, and then the predictor of interest was entered. I don't think this is a helpful way to think about it, but it would make it fit under the rubric of a hierarchical regression.
    “In God we trust. All others must bring data.”
    ~W. Edwards Deming

  8. #8
    Points: 95, Level: 1
    Level completed: 90%, Points required for next Level: 5

    Posts
    13
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Re: hierarchical regression for controlling variables?

    Oke

    independent variable: stress
    dependent variable: eating
    control variables: gender, education and age

    Thus: regressing stress on eating, while controlling for the effects of gender, education and age.
    Note that I found that gender, education and age did not explain any variance in eating (model 1 was insignificant).

  9. #9
    Points: 95, Level: 1
    Level completed: 90%, Points required for next Level: 5

    Posts
    13
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Re: hierarchical regression for controlling variables?

    Quote Originally Posted by Jake View Post
    Just describe it in terms of which variables are or are not controlled for. That is the most straightforward and easy to understand description.

    YES! that is exactly what I mean

    Can I report that I used hierarchical regression, then?

  10. #10
    Cookie Scientist
    Points: 13,431, Level: 75
    Level completed: 46%, Points required for next Level: 219
    Jake's Avatar
    Location
    Austin, TX
    Posts
    1,293
    Thanks
    66
    Thanked 584 Times in 438 Posts

    Re: hierarchical regression for controlling variables?

    Like I said earlier, I wouldn't.
    “In God we trust. All others must bring data.”
    ~W. Edwards Deming

  11. #11
    Points: 95, Level: 1
    Level completed: 90%, Points required for next Level: 5

    Posts
    13
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Re: hierarchical regression for controlling variables?

    Quote Originally Posted by Jake View Post
    Like I said earlier, I wouldn't.
    Oke, So it is oke to just mention that I did a standard multiple regression analysis while controlling for the effects of gender, education and age?

    For me this also more beneficial since I am not familiar with hierarchical regression analysis at all...

  12. #12
    Cookie Scientist
    Points: 13,431, Level: 75
    Level completed: 46%, Points required for next Level: 219
    Jake's Avatar
    Location
    Austin, TX
    Posts
    1,293
    Thanks
    66
    Thanked 584 Times in 438 Posts

    Re: hierarchical regression for controlling variables?

    In my opinion, absolutely.
    “In God we trust. All others must bring data.”
    ~W. Edwards Deming

  13. #13
    Omega Contributor
    Points: 38,253, Level: 100
    Level completed: 0%, Points required for next Level: 0
    hlsmith's Avatar
    Location
    Not Ames, IA
    Posts
    6,989
    Thanks
    397
    Thanked 1,185 Times in 1,146 Posts

    Re: hierarchical regression for controlling variables?

    Seems like a good plan. It does not seem like hierarchical regression. I refereed a manuscript a couple of weeks ago and they said they used hierarchical regression and it seemed like what Jake described. My critique was to better describe the model and why it was hierarchical. Were fixed or random effects incorporated?

  14. #14
    Points: 95, Level: 1
    Level completed: 90%, Points required for next Level: 5

    Posts
    13
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Re: hierarchical regression for controlling variables?

    Thank you!

    How should I interpret the model after including the control variables? Should I look to Block 2 of the table (with all variables included) and check the R squared value instead of the R square change value?

  15. #15
    Points: 95, Level: 1
    Level completed: 90%, Points required for next Level: 5

    Posts
    13
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Re: hierarchical regression for controlling variables?


    Quote Originally Posted by hlsmith View Post
    Seems like a good plan. It does not seem like hierarchical regression. I refereed a manuscript a couple of weeks ago and they said they used hierarchical regression and it seemed like what Jake described. My critique was to better describe the model and why it was hierarchical. Were fixed or random effects incorporated?
    I guess fixed but i am not sure

+ Reply to Thread
Page 1 of 2 1 2 LastLast

           




Posting Permissions

  • You may not post new threads
  • You may not post replies
  • You may not post attachments
  • You may not edit your posts






Advertise on Talk Stats